Network medicine: a network-based approach to human disease

In the citing paper

“Few genes act in isolation but rather affect the function of other genes to influence a particular phenotype via in cellular networks or pathways (Barabasi et al., 2011; Geschwind and Konopka, 2009).”

In the citing paper

“Communities of co-expressed proteins can be linked to disease processes, and the most strongly correlated proteins, or “hubs,” within these co-expression modules are enriched in key drivers of disease pathogenesis5–10.”

In the citing paper

“Machine learning has been used to analyze high-throughput molecular interactomes to unravel genetic architecture perturbed in disease12,13 and help design therapies to target them14.”

In the citing paper

“This evaluation method aligns with the approach predominantly used in the literature12,14–16,18–20.”

In the citing paper

“TxGNN leverages an additional metric learning component for zero-shot prediction, capitalizing on the insight that diseases can share disease-associated genetic and genomic networks10,14 and, thus, medical knowledge of disease-associated networks can be transferred by the model from well-annotated diseases to other diseases to enhance predictions on diseases with limited treatment options (Fig. 2a”

In the citing paper

“In protein interaction networks, for instance, mutations in interacting proteins often lead to similar diseases [13].”

In the citing paper

“Further, essential genes are often found in hubs of a molecular network whereas non-essential genes (e.g., those associated with disease) are located on the periphery [13].”

In the citing paper

“Given by the shared components and disease module hypotheses [13], cellular components associated with the same phenotype tend to cluster in the same network neighborhood [16].”

In the citing paper

“Thus, the network parsimony principle dictates that shortest molecular paths between known disease-associated components tend to correlate with causal molecular pathways [13].”

In the citing paper

“First, interacting entities are typically more similar than non-interacting entities, as implicated by the local hypothesis [13].”

In the citing paper

“The organizing principles governing networks link network structure to molecular phenotypes, biological roles, disease, and health, thus providing the conceptual grounding that, we argue, can explain the successes (and limitations) of graph representation learning and inform future development of the field.”

In the citing paper

“Because such processes are costly and time-consuming, in silico approaches have been adopted into the drug discovery pipeline.”

In the citing paper

“Modern drug discovery requires elucidating a candidate drug’s chemical structure, identifying its drug targets, quantifying its efficacy and toxicity, and detecting its potential side effects [13, 14, 32, 164].”